When Every Minute Counts: Predicting Pre-Hospital Deliveries and Neonatal Risk in Emergency Medical Services Using Data-Driven Models

分秒必争:利用数据驱动模型预测院前分娩和新生儿风险(急救医疗服务)

阅读:4

Abstract

Background/Objectives: Pre-hospital delivery is an unpredictable event posing significant challenges for Emergency Medical Services (EMS) teams. Despite advances in perinatal care, emergency deliveries outside the hospital environment remain associated with increased maternal and neonatal risks. This study aimed to identify predictors of out-of-hospital delivery in EMS-attended labor cases and determinants of neonatal condition immediately after delivery. Methods: We conducted a retrospective analysis of 5097 EMS records of laboring women in Poland from August 2021 to January 2022, of which 2927 were included in the final study sample. Multivariate logistic regression models with multiple imputation for missing data were used to identify predictors of pre-hospital delivery and adverse neonatal condition (Apgar ≤ 7) in EMS-managed childbirths. Results: Pre-hospital delivery was strongly associated with second-stage labor (OR ≈ 535; p < 0.0001), ruptured membranes (OR ≈ 8.7; p < 0.0001), and fewer previous pregnancies (OR = 0.86; p = 0.018), and showed a trend with higher maternal heart rate (OR = 1.015; p = 0.083). Neonatal status classified as Apgar ≤ 7 was significantly associated with preterm birth (p < 0.0001), absence of fetal movements (OR ≈ 26.4; p = 0.025), and complications during pregnancy (p = 0.036). Complications during labor and lack of prenatal care were not significantly associated with increased risk of pre-hospital delivery in the model. Conclusions: Rupture of membranes, second-stage labor, and fewer previous pregnancies are significant predictors of pre-hospital delivery in EMS-managed cases. Absence of fetal movements and preterm gestation predict worse neonatal outcomes (Apgar ≤ 7). Early identification of these factors may enhance prehospital perinatal care and improve maternal and neonatal prognosis.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。